arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.07752cs.LGstat.ML
收藏

使用动态自动编码器的深度聚类:从重构到质心构建

Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction

National Engineering School of Tunis(突尼斯国立工程师学院);University of Tunis El Manar(突尼斯埃尔马纳尔大学);Ryerson University(瑞尔森大学);Higher School of Communication of Tunis(突尼斯高等通信学院);University of Carthage(迦太基大学)

Nairouz Mrabah, Naimul Mefraz Khan, Riadh Ksantini, Zied Lachiri

摘要:

在无监督学习中,没有明显的直接成本函数可以捕获变化和相似性的重要因素。由于自然系统具有平滑的动态特性,如果无监督的目标函数在训练过程中保持静态,则会失去机会。缺乏具体的监督表明,应该整合平稳的动态。与经典的静态成本函数相比,动态目标函数允许更好地利用通过伪监督获得的渐进和不确定的知识。在本文中,我们提出了动态自动编码器(DynAE),这是一种新的深度聚类模型,通过逐渐平滑地消除重建目标函数,以利于构建目标函数,从而克服了聚类-重建权衡。在基准数据集上的实验评估表明,与最相关的深度聚类方法相比,我们的方法实现了最先进的结果。

英文摘要:

In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities. Since natural systems have smooth dynamics, an opportunity is lost if an unsupervised objective function remains static during the training process. The absence of concrete supervision suggests that smooth dynamics should be integrated. Compared to classical static cost functions, dynamic objective functions allow to better make use of the gradual and uncertain knowledge acquired through pseudo-supervision. In this paper, we propose Dynamic Autoencoder (DynAE), a novel model for deep clustering that overcomes a clustering-reconstruction trade-off, by gradually and smoothly eliminating the reconstruction objective function in favor of a construction one. Experimental evaluations on benchmark datasets show that our approach achieves state-of-the-art results compared to the most relevant deep clustering methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑